CFD & Thermal Simulation Expert | Scientific Machine Learning, Physics-Informed AI (PINNs) & Python Engineering Solutions
I am a Mechanical Engineering Researcher and Scientific Computing Specialist with over 10 years of experience in fluid mechanics, thermal-fluid systems, and advanced numerical modeling. I hold a PhD in Fluid Mechanics and specialize in bridging traditional computational mechanics with cutting-edge artificial intelligence.
Core Technical Expertise:
• Computational Fluid Dynamics (CFD) & Thermal Analysis: High-fidelity 3D/2D flow simulations, heat transfer, conjugate heat transfer (CHT), turbulence modeling (k-epsilon, SST k-omega), and internal/external flow analysis using ANSYS Fluent, OpenFOAM, and SolidWorks Flow.
• Scientific Machine Learning (SciML) & Physics-Informed AI: Development of Physics-Informed Neural Networks (PINNs), forward and inverse flow field reconstruction, surrogate modeling, and reduced-order models using PyTorch, TensorFlow, and DeepXDE.
• Scientific Computing & Custom Automation: Writing efficient Python algorithms for numerical optimization, continuous-data post-processing, automated simulation pipelines, and parametric design evaluation.
I am committed to providing clear technical reports, rigorous validation, clean code, and actionable engineering insights. Whether you need a full CFD design optimization or an AI-driven physics surrogate model, I deliver research-grade performance for your engineering projects.
Work Terms
• Communication: Open and responsive communication via Guru chat. Technical progress reports and interim deliverables provided for all milestones.
• Payment Terms: Prefer Milestone Payment fixed-price contracts or hourly tracking via Guru, with project scopes clearly defined prior to commencement.
• Deliverables: Complete simulation files, raw data, processed visualization plots/videos, source code (Python/PyTorch), and a comprehensive engineering report included with every project.